Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 14723
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS layout structure cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.91
    曖昧さ回避
    -0.72
    protoimpl
    -0.70
    Chham
    -0.68
    cshtml
    -0.67
    ьаж
    -0.67
    rawDesc
    -0.67
    IVEREF
    -0.66
    slidesToShow
    -0.66
    XmlAccessorType
    -0.66
    POSITIVE LOGITS
    Kanpo
    0.45
    ális
    0.43
     sebelah
    0.43
    mrt
    0.42
    wijl
    0.41
    ότε
    0.41
    cely
    0.40
    prow
    0.40
     or
    0.39
    一个小
    0.39
    Activations Density 0.034%

    No Known Activations